What Goes in CLAUDE.md, and What Belongs in an ADR
You read the previous post and pasted the why into CLAUDE.md, and now that paragraph rides along on every task the agent ever runs. The sign belongs there. The reason doesn’t.
LLM
ADRs for AI-Assisted Codebases: Write Down Why, or the Agent Will Undo It
ADRs were written for the future engineer who asks ‘why is it like this?’ That engineer is now an AI agent, it arrives in minutes instead of years, and it doesn’t ask - it refactors.
JavaScript Necromancy: The Web Never Forgets, and Now It Autocompletes
LLMs learned JavaScript from a web that never deletes anything. Now they generate 2013’s best practices at scale, publish them back onto the web, and the next model learns from that. The graveyard has a feedback loop.
Context Is an Architectural Surface
Context isn’t what you paste into the prompt. It’s what the model sees, prioritizes, and is constrained by. That’s not prompting — that’s system design.
Stop Betting on One-Shot: A Practical Workflow for Shipping with LLMs
LLMs don’t ship software. They ship text. You ship software by constraining the problem until text reliably becomes change sets you can trust.
Why AI Still Sucks at Your Job (and Why That Won't Last)
The bottleneck was never intelligence. It was instrumentation. Once we learn to define what systems should do, the execution becomes trivial.
While everyone Is Talking About AI, GAC Is Coming for Your Job
Large Language Models are best described as GAC — Glorified Auto-Complete. If Google Search Suggest was the ape, LLMs are the upright-walking hominid.